MensBeam
/
lax
3
0
Fork 0
Code Issues 3 Pull Requests Releases Activity
Browse Source

Add abstract Feed class as common base for XML and JSON feeds

master
J. King 6 years ago
parent
a6219a95b2
commit
26ceb68acd
4 changed files with 101 additions and 55 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 61
      lib/Feed.php
  2. 26
      lib/XML/Construct.php
  3. 37
      lib/XML/Feed.php
  4. 32
      lib/XML/XPath.php

61
lib/Feed.php
View File

@ -0,0 +1,61 @@
<?php
/** @license MIT
* Copyright 2018 J. King et al.
* See LICENSE and AUTHORS files for details */
declare(strict_types=1);
namespace JKingWeb\Lax;
use JKingWeb\Lax\Person\Person;
use JKingWeb\Lax\Person\Collection as PersonCollection;
abstract class Feed {
public $type;
public $version;
public $url;
public $link;
public $title;
public $summary;
public $categories;
public $people;
public $author;
/** Constructs a parsed feed */
abstract public function __construct(string $data, string $contentType = "", string $url = "");
/** Parses the feed to extract sundry metadata */
protected function parse() {
$this->id = $this->getId();
$this->link = $this->getLink();
$this->title = $this->getTitle();
$this->summary = $this->getSummary();
$this->people = $this->getPeople();
$this->author = $this->people->primary();
// do a second pass on missing data we'd rather fill in
$this->link = strlen($this->link) ? $this->link : $this->url;
$this->title = strlen($this->title) ? $this->title : $this->link;
}
/** General function to fetch the feed title */
abstract public function getTitle(): string;
/** General function to fetch the feed's Web-representation URL */
abstract public function getLink(): string;
/** General function to fetch the description of a feed */
abstract public function getSummary(): string;
/** General function to fetch the categories of a feed
*
* If the $grouped parameter is true, and array of arrays will be returned, keyed by taxonomy/scheme
*
* The $humanFriendly parameter only affects Atom categories
*/
abstract public function getCategories(bool $grouped = false, bool $humanFriendly = true): array;
/** General function to fetch the feed identifier */
abstract public function getId(): string;
/** General function to fetch a collection of people associated with a feed */
abstract public function getPeople(): PersonCollection;
}

26
lib/XML/Construct.php
View File

@ -8,37 +8,13 @@ namespace JKingWeb\Lax\XML;
use JKingWeb\Lax\Person\Person;
abstract class Construct {
trait Construct {
/** @var \DOMDocument */
public $document;
/** @var \DOMXPath */
protected $xpath;
/** @var \DOMElement */
protected $subject;
const NS = [
'atom' => "http://www.w3.org/2005/Atom", // Atom syndication format https://tools.ietf.org/html/rfc4287
'rss1' => "http://purl.org/rss/1.0/", // RDF site summary 1.0 http://purl.org/rss/1.0/spec
'rss0' => "http://channel.netscape.com/rdf/simple/0.9/", // RDF Site Summary 0.90 http://www.rssboard.org/rss-0-9-0
'dc' => "http://purl.org/dc/elements/1.1/", // Dublin Core metadata http://purl.org/rss/1.0/modules/dc/
'sched' => "http://purl.org/rss/1.0/modules/syndication/", // Syndication schedule extension http://purl.org/rss/1.0/modules/syndication/
'enc' => "http://purl.org/rss/1.0/modules/content/", // Explicitly encoded content extension http://purl.org/rss/1.0/modules/content/
'media' => "http://search.yahoo.com/mrss/", // Embedded media extension http://www.rssboard.org/media-rss
// RSS 2.0 does not have a namespace // Really Simple Syndication 2.0.11 http://www.rssboard.org/rss-specification
'rdf' => "http://www.w3.org/1999/02/22-rdf-syntax-ns#", // Resource Description Framework
'xhtml' => "http://www.w3.org/1999/xhtml", // XHTML
'apple' => "http://www.itunes.com/dtds/podcast-1.0.dtd", // iTunes podcasts https://help.apple.com/itc/podcasts_connect/#/itcb54353390
'gplay' => "http://www.google.com/schemas/play-podcasts/1.0", // Google Play podcasts https://support.google.com/googleplay/podcasts/answer/6260341
];
/** Returns an XPath processor with various necessary namespace prefixes defined */
public static function getXPathProcessor(\DOMDocument $doc): \DOMXPath {
$proc = new \DOMXPath($doc);
foreach (self::NS as $prefix => $url) {
$proc->registerNamespace($prefix, $url);
}
return $proc;
}
/** Trims plain text and collapses whitespace */
protected function trimText(string $text): string {

37
lib/XML/Feed.php
View File

@ -9,19 +9,10 @@ namespace JKingWeb\Lax\XML;
use JKingWeb\Lax\Person\Person;
use JKingWeb\Lax\Person\Collection as PersonCollection;
class Feed extends Construct {
class Feed extends \JKingWeb\Lax\Feed {
use Construct;
use Primitives\Construct;
use Primitives\Feed;
public $type;
public $version;
public $url;
public $link;
public $title;
public $summary;
public $categories;
public $people;
public $author;
/** Constructs a parsed feed */
public function __construct(string $data, string $contentType = "", string $url = "") {
@ -34,7 +25,7 @@ class Feed extends Construct {
$this->document = new \DOMDocument();
$this->document->loadXML($data, \LIBXML_BIGLINES | \LIBXML_COMPACT);
$this->document->documentURI = $url;
$this->xpath = self::getXPathProcessor($this->document);
$this->xpath = new XPath($this->document);
$this->subject = $this->document->documentElement;
$ns = $this->subject->namespaceURI;
$name = $this->subject->localName;
@ -42,39 +33,25 @@ class Feed extends Construct {
$this->subject = $this->fetchElement("./channel") ?? $this->subject;
$this->type = "rss";
$this->version = $this->document->documentElement->getAttribute("version");
} elseif ($ns==self::NS['rdf'] && $name=="RDF") {
} elseif ($ns==XPath::NS['rdf'] && $name=="RDF") {
$this->type = "rdf";
$channel = $this->fetchElement("./rss1:channel|./rss0:channel");
if ($channel) {
$this->subject = $channel;
$this->version = ($channel->namespaceURI==self::NS['rss1']) ? "1.0" : "0.90";
$this->version = ($channel->namespaceURI==XPath::NS['rss1']) ? "1.0" : "0.90";
} else {
$element = $this->fetchElement("./rss1:item|./rss0:item|./rss1:image|./rss0:image");
if ($element) {
$this->version = ($element->namespaceURI==self::NS['rss1']) ? "1.0" : "0.90";
$this->version = ($element->namespaceURI==XPath::NS['rss1']) ? "1.0" : "0.90";
}
}
} elseif ($ns==self::NS['atom'] && $name=="feed") {
} elseif ($ns==XPath::NS['atom'] && $name=="feed") {
$this->type = "atom";
$this->version = "1.0";
} else {
throw new \Exception;
}
$this->url = $url;
}
/** Parses the feed to extract sundry metadata */
protected function parse() {
$this->id = $this->getId();
$this->link = $this->getLink();
$this->title = $this->getTitle();
$this->summary = $this->getSummary();
$this->people = $this->getPeople();
$this->author = $this->people->primary();
// do a second pass on missing data we'd rather fill in
$this->link = strlen($this->link) ? $this->link : $this->url;
$this->title = strlen($this->title) ? $this->title : $this->link;
}
/** General function to fetch the feed title */

32
lib/XML/XPath.php
View File

@ -0,0 +1,32 @@
<?php
/** @license MIT
* Copyright 2018 J. King et al.
* See LICENSE and AUTHORS files for details */
declare(strict_types=1);
namespace JKingWeb\Lax\XML;
class XPath extends \DOMXpath {
const NS = [
'atom' => "http://www.w3.org/2005/Atom", // Atom syndication format https://tools.ietf.org/html/rfc4287
'rss1' => "http://purl.org/rss/1.0/", // RDF site summary 1.0 http://purl.org/rss/1.0/spec
'rss0' => "http://channel.netscape.com/rdf/simple/0.9/", // RDF Site Summary 0.90 http://www.rssboard.org/rss-0-9-0
'dc' => "http://purl.org/dc/elements/1.1/", // Dublin Core metadata http://purl.org/rss/1.0/modules/dc/
'sched' => "http://purl.org/rss/1.0/modules/syndication/", // Syndication schedule extension http://purl.org/rss/1.0/modules/syndication/
'enc' => "http://purl.org/rss/1.0/modules/content/", // Explicitly encoded content extension http://purl.org/rss/1.0/modules/content/
'media' => "http://search.yahoo.com/mrss/", // Embedded media extension http://www.rssboard.org/media-rss
// RSS 2.0 does not have a namespace // Really Simple Syndication 2.0.11 http://www.rssboard.org/rss-specification
'rdf' => "http://www.w3.org/1999/02/22-rdf-syntax-ns#", // Resource Description Framework
'xhtml' => "http://www.w3.org/1999/xhtml", // XHTML
'apple' => "http://www.itunes.com/dtds/podcast-1.0.dtd", // iTunes podcasts https://help.apple.com/itc/podcasts_connect/#/itcb54353390
'gplay' => "http://www.google.com/schemas/play-podcasts/1.0", // Google Play podcasts https://support.google.com/googleplay/podcasts/answer/6260341
];
/** Returns an XPath processor with various necessary namespace prefixes defined */
public function __construct(\DOMDocument $doc) {
parent::__construct($doc);
foreach (XPath::NS as $prefix => $url) {
$this->registerNamespace($prefix, $url);
}
}
}
Write Preview
Loading…
Cancel
Save